from __future__ import absolute_import, division, unicode_literals from pip._vendor.six import with_metaclass, viewkeys import types from collections import OrderedDict from . import _inputstream from . import _tokenizer from . import treebuilders from .treebuilders.base import Marker from . import _utils from .constants import ( spaceCharacters, asciiUpper2Lower, specialElements, headingElements, cdataElements, rcdataElements, tokenTypes, tagTokenTypes, namespaces, htmlIntegrationPointElements, mathmlTextIntegrationPointElements, adjustForeignAttributes as adjustForeignAttributesMap, adjustMathMLAttributes, adjustSVGAttributes, E, _ReparseException ) def parse(doc, treebuilder="etree", namespaceHTMLElements=True, **kwargs): """Parse an HTML document as a string or file-like object into a tree :arg doc: the document to parse as a string or file-like object :arg treebuilder: the treebuilder to use when parsing :arg namespaceHTMLElements: whether or not to namespace HTML elements :returns: parsed tree Example: >>> from html5lib.html5parser import parse >>> parse('

This is a doc